Created
January 27, 2015 09:40
-
-
Save escapeboy/b6b709e11e1dec52342e to your computer and use it in GitHub Desktop.
PHP Truncate text preserving html tags by Jonas Raoni Soares Silva
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
//+ Jonas Raoni Soares Silva | |
//@ http://jsfromhell.com | |
function truncate($text, $length, $suffix = '…', $isHTML = true) { | |
$i = 0; | |
$simpleTags=array('br'=>true,'hr'=>true,'input'=>true,'image'=>true,'link'=>true,'meta'=>true); | |
$tags = array(); | |
if($isHTML){ | |
preg_match_all('/<[^>]+>([^<]*)/', $text, $m, PREG_OFFSET_CAPTURE | PREG_SET_ORDER); | |
foreach($m as $o){ | |
if($o[0][1] - $i >= $length) | |
break; | |
$t = substr(strtok($o[0][0], " \t\n\r\0\x0B>"), 1); | |
// test if the tag is unpaired, then we mustn't save them | |
if($t[0] != '/' && (!isset($simpleTags[$t]))) | |
$tags[] = $t; | |
elseif(end($tags) == substr($t, 1)) | |
array_pop($tags); | |
$i += $o[1][1] - $o[0][1]; | |
} | |
} | |
// output without closing tags | |
$output = substr($text, 0, $length = min(strlen($text), $length + $i)); | |
// closing tags | |
$output2 = (count($tags = array_reverse($tags)) ? '</' . implode('></', $tags) . '>' : ''); | |
// Find last space or HTML tag (solving problem with last space in HTML tag eg. <span class="new">) | |
$pos = (int)end(end(preg_split('/<.*>| /', $output, -1, PREG_SPLIT_OFFSET_CAPTURE))); | |
// Append closing tags to output | |
$output.=$output2; | |
// Get everything until last space | |
$one = substr($output, 0, $pos); | |
// Get the rest | |
$two = substr($output, $pos, (strlen($output) - $pos)); | |
// Extract all tags from the last bit | |
preg_match_all('/<(.*?)>/s', $two, $tags); | |
// Add suffix if needed | |
if (strlen($text) > $length) { $one .= $suffix; } | |
// Re-attach tags | |
$output = $one . implode($tags[0]); | |
//added to remove unnecessary closure | |
$output = str_replace('</!-->','',$output); | |
return $output; | |
} | |
?> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment